Spatio-Temporal Missing Data Reconstruction by Using Deep Neural Networks in Agricultural Monitoring Systems

Mehmet Selahaddin Sentop*, Meric Yucel, Burak Berk Ustundag

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

This study addresses the issue of missing, distorted, or inaccurate data in agricultural monitoring systems. Such data issues can lead to errors in prediction and management models, affecting various applications in agricultural meteorology and remote sensing. Conventional missing data completion algorithms often fail to effectively leverage the inherent relationships between temporal and spatial data in agricultural observation systems. Machine learning techniques, specifically deep learning, offer a promising solution by considering factors such as time windows, seasons, and plant characteristics to fill missing data. However, managing the non-linear nature of agricultural monitoring within a machine learning framework poses a challenge. This study proposes a new deep learning approach called Predictive Error Compensated Network that addresses missing data reconstruction while mitigating overfitting. Predictive Error Compensated Network utilizes feature extraction networks and Discrete Wavelet Transform to incorporate different data types and time windows, improving performance. Evaluation against traditional methods demonstrated superior results with Predictive Error Compensated Network, achieving a significant reduction in reconstruction Root Mean Squared Error across different time windows.

Original languageEnglish
Title of host publication2023 11th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350303513
DOIs
Publication statusPublished - 2023
Event11th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2023 - Wuhan, China
Duration: 25 Jul 202328 Jul 2023

Publication series

Name2023 11th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2023

Conference

Conference11th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2023
Country/TerritoryChina
CityWuhan
Period25/07/2328/07/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Funding

This work was supported by the research project ”Platform Development for Neuromorphic Computing and Next Generation Programming” of Istanbul Technical University, National Software Certification Research Center.

FundersFunder number
National Software Certification Research Center
Istanbul Teknik Üniversitesi

    Keywords

    • Agricultural Monitoring Systems
    • Data Reconstruction
    • Discrete Wavelet Transform
    • Error Compensation

    Fingerprint

    Dive into the research topics of 'Spatio-Temporal Missing Data Reconstruction by Using Deep Neural Networks in Agricultural Monitoring Systems'. Together they form a unique fingerprint.

    Cite this